Gemini 2.5 Flash

GA

Output: text only. Audio input priced higher: input $0.30 (text/image/video) / $1.00 (audio); cached input $0.03 (text/image/video) / $0.10 (audio) per 1M tokens (values shown are text/image/video tier). NOT DEPRECATED, per Google, as of the 2026-10-20 read: the model page now opens with the note "To ensure reliable performance for everyone, we are limiting access to the 2.5 models to users who have actively used them in the past. These models are not deprecated and will continue to be served until further notice through the API. For any new projects, use our latest models: 3.5 Flash-Lite or 3.8 Flash. This helps us maintain sufficient capacity for both ongoing legacy workflows and new applications.", and the deprecations table row for gemini-2.5-flash reads "No shutdown date announced" with an empty Recommended replacement cell (the row is not gray). Status is therefore ga, retires_on and replacement are null, and the access restriction is recorded here because the schema has no field for it: a project that has not used the 2.5 models before may be unable to call this endpoint. Until 2026-10-19 the same table gave shutdown October 16, 2026 and gemini-3.6-flash as the recommended replacement (gemini-3.5-flash until Google re-pointed it on 2026-07-31), and this row carried both with status deprecated; that date passed on 2026-10-16 without a gray marker, and Google has now withdrawn it rather than acted on it (Google publishes shutdown dates as "the earliest possible dates on which a model might be retired"). Google does not date the edit; the deprecations page says Last updated 2026-10-20 UTC, and the API changelog has no entry for it. The pricing page still carries the section with the rates above. Deprecations page release date: 2025-06-17. Latest update June 2025.

Gemini 2.5 Flash by Google costs $0.3 per 1M input tokens and $2.50 per 1M output tokens ($0.85/1M blended), with a 1.0M (1.048.576-token) context window. It is generally available (GA), with a knowledge cutoff of Jan 2025.

Last verified: 24 Oct 2026 · sourced from official provider documentation

Provider
Google
Status
GA
Input price
$0.3 / 1M tokens
Output price
$2.50 / 1M tokens
Cached input
$0.03 / 1M tokens
Blended price
$0.85 / 1M tokens
Context window
1.048.576 tokens (1.0M)
Max output
65.536 tokens
Modality
text, image, video, audio
Open weights
No — API only
Knowledge cutoff
2025-01
Released
17 Jun 2025
API string
gemini-2.5-flash

Source: Google official documentation ↗

FAQ

Gemini 2.5 Flash — questions & answers

How much does Gemini 2.5 Flash cost?

Gemini 2.5 Flash is priced at $0.3 per 1M input tokens and $2.50 per 1M output tokens ($0.85/1M blended at a 3:1 input-to-output ratio), with cached input at $0.03 per 1M tokens.

What is the context window of Gemini 2.5 Flash?

Gemini 2.5 Flash has a 1.048.576-token context window (1.0M), with up to 65.536 output tokens per request.

Is Gemini 2.5 Flash deprecated?

No — Gemini 2.5 Flash is generally available (GA) and not currently scheduled for deprecation or retirement in our tracker.

Does Gemini 2.5 Flash support image or vision input?

Yes — Gemini 2.5 Flash accepts image input. Listed modalities: text, image, video, audio.

Can I self-host Gemini 2.5 Flash?

No — Gemini 2.5 Flash is proprietary. Its weights are not publicly released, so it is available only through Google's API (or hosted partners), not for self-hosting.

What is the API model string for Gemini 2.5 Flash?

The API model identifier for Gemini 2.5 Flash is "gemini-2.5-flash" when calling Google's API.

What is Gemini 2.5 Flash's knowledge cutoff?

Gemini 2.5 Flash's training knowledge cutoff is Jan 2025.